© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 44589
    Prev
    Next
    INDEX
    Explanations

    convection or flow movement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    pector
    -0.08
    aglia
    -0.08
    abend
    -0.07
    oproject
    -0.07
    eness
    -0.07
    chaft
    -0.07
    æ£ĢæŁ¥ç»Ħ
    -0.07
     retrouv
    -0.07
    arkin
    -0.07
    éŀŃçĤ®
    -0.07
    POSITIVE LOGITS
     transport
    0.08
    à¸ŀา
    0.08
     поÑĤо
    0.07
     flow
    0.07
    ä¸įçķħ
    0.07
    对æµģ
    0.07
    ör
    0.07
    ä¸įæģ¯
    0.07
     velocity
    0.07
     flows
    0.06
    Activations Density 0.008%

    No Known Activations